Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to news and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asser
    -0.16
    ping
    -0.16
    ARING
    -0.14
    ger
    -0.14
    yun
    -0.14
    ame
    -0.14
    iap
    -0.13
     complain
    -0.13
    OrElse
    -0.13
    uestion
    -0.13
    POSITIVE LOGITS
    letters
    0.27
    flash
    0.21
    room
    0.19
    feed
    0.17
    .soft
    0.17
    lett
    0.16
    usta
    0.16
    åĭĻ
    0.16
    brief
    0.15
    eus
    0.15
    Act Density 0.023%

    No Known Activations